AI chatbots make it possible for people who can’t code to build apps, sites and tools. But it’s decidedly problematic.

Four vulnerabilities in CrewAI could be chained together via prompt injection for sandbox escape, remote code execution, and ...

Build your first fully functional, Java-based AI agent using familiar Spring conventions and built-in tools from Spring AI.

Unsafe defaults in MCP configurations open servers to possible remote code execution, according to security researchers who ...

Strapi plugins exploit Redis and PostgreSQL via postinstall scripts, enabling persistent access and data theft.

A North Korea-nexus threat actor compromised the widely used axios npm package, delivering a cross-platform remote access trojan to potentially millions of developer environments during a three-hour ...

M stolen after six-month DPRK social engineering campaign began fall 2025, exposing Drift’s contributors and cloud assets.

IntroductionOn March 31, 2026, Anthropic accidentally exposed the full source code of Claude Code (its flagship terminal-based AI coding agent) through a 59.8 MB JavaScript source map (.map) file ...

With almost 175,000 npm projects listing the library as a dependency, the attack had a huge cascade effect and shows how quickly a compromised package can propagate through the ecosystem.

Open WebUI has been getting some great updates, and it's a lot better than ChatGPT's web interface at this point.

The maintainer account for the axios package on npm was compromised to inject a remote access trojan for Windows, macOS, and Linux.

MCP is the MVP.